paper-with-me

Papers

Computer Vision Model Compression Techniques for Embedded Systems: A Survey

2024-08-15 · Alexandre Lopes, Fernando Pereira dos Santos, Diulhio de Oliveira, Mauricio Schiezaro, Helio Pedrini

Deep neural networks have consistently represented the state of the art in most computer vision problems. In these scenarios, larger and more complex models have demonstrated superior performance to smaller architectures, especially when trained with plenty of representative data. With the recent adoption of Vision Transformer (ViT) based architectures and advanced Convolutional Neural Networks (CNNs), the total number of parameters of leading backbone architectures increased from 62M parameters in 2012 with AlexNet to 7B parameters in 2024 with AIM-7B. Consequently, deploying such deep architectures faces challenges in environments with processing and runtime constraints, particularly in embedded systems. This paper covers the main model compression techniques applied for computer vision tasks, enabling modern models to be used in embedded systems. We present the characteristics of compression subareas, compare different approaches, and discuss how to choose the best technique and expected variations when analyzing it on various embedded devices. We also share codes to assist researchers and new practitioners in overcoming initial implementation challenges for each subarea and present trends for Model Compression. Case studies for compression models are available at \href{https://github.com/venturusbr/cv-model-compression}{https://github.com/venturusbr/cv-model-compression}.

📄 PDF Abstract BibTeX arXiv:2408.08250

Code (1)

venturusbr/cv-model-compression 공식 구현 pytorch

Tasks

Model CompressionSurvey

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference

2018-10-21 · Qing Qin, Jie Ren, Jialong Yu, Ling Gao 외

The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression te…

Deep Learningimage-classificationImage ClassificationModel Compression+1

Adversarial Attacks on Machine Learning in Embedded and IoT Platforms

2023-03-03 · Christian Westbrook, Sudeep Pasricha

Machine learning (ML) algorithms are increasingly being integrated into embedded and IoT systems that surround us, and they are vulnerable to adversarial attacks. The deployment of these ML algorithms on resource-limited…

Adversarial RobustnessModel Compression

Embedded Systems and Computer Vision Techniques utilized in Spray Painting Robots: A Review

2020-10-02 · Soham Shah, Siddhi Vinayak Pandey, Archit Sorathiya, Raj Sheth 외

The advent of the era of machines has limited human interaction and this has increased their presence in the last decade. The requirement to increase the effectiveness, durability and reliability in the robots has also r…

Edge Detectionobject-detectionObject Detection

Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions

2025-12-31 · Itallo Patrick Castro Alves Da Silva, Emanuel Adler Medeiros Pereira, Erick de Andrade Barboza, Baldoino Fonseca dos Santos Neto 외 arxiv

Compressed deep learning models are crucial for deploying computer vision systems on resource-constrained devices. However, model compression may affect robustness, especially under natural corruption. Therefore, it is i…

Model Compression

A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion

2025-01-13 · Fabio Montello, Ronja Güldenring, Simone Scardapane, Lazaros Nalpantidis

Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have…

Dynamic neural networksModel CompressionSensor Fusion